Cardiorespiratory Model-Based Data-Driven Approach for Sleep Apnea Detection

• Published in: IEEE journal of biomedical and health informatics Vol. 22; no. 4; pp. 1036 - 1045
• Main Authors: Gutta, Sandeep, Cheng, Qi, Nguyen, Hoa Dinh, Benjamin, Bruce A.
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.07.2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Apnea; Biomedical measurement; Cardiorespiratory system mathematical model; Covariance; Electrocardiography; Feature extraction; Gaussian process; Gaussian process state-space model; Health problems; Heart rate; Kernel functions; Likelihood ratio; Mathematical analysis; Mathematical model; Mathematical models; multimodal sensor fusion; Oxygen content; Physiology; Signal processing; Sleep; Sleep apnea; sleep apnea detection; Sleep disorders; Wearable technology
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2017.2740120

Obstructive sleep apnea (OSA) is a chronic sleep disorder affecting millions of people worldwide. Individuals with OSA are rarely aware of the condition and are often left untreated, which can lead to some serious health problems. Nowadays, several low-cost wearable health sensors are available that can be used to conveniently and noninvasively collect a wide range of physiological signals. In this paper, we propose a new framework for OSA detection in which we combine the wearable sensor measurement signals with the mathematical models of the cardiorespiratory system. Vector-valued Gaussian processes (GPs) are adopted to model the physiological variations among different individuals. The GP covariance is constructed using the sum of separable kernel functions, and the GP hyperparameters are estimated by maximizing the marginal likelihood function. A likelihood ratio test is proposed to detect OSA using the widely available heart rate and peripheral oxygen saturation (SpO<inline-formula><tex-math notation="LaTeX">_2</tex-math> </inline-formula>) measurement signals. We conduct experiments on both synthetic and real data to show the effectiveness of the proposed OSA detection framework compared to purely data-driven approaches.